© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64384
    Prev
    Next
    INDEX
    Explanations

    lymph nodes and throat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çģ¶
    -0.09
    èĦļ趾
    -0.07
    éĵº
    -0.07
    å·«
    -0.07
    åĩºè½¨
    -0.07
     toes
    -0.07
    èĬĿ
    -0.06
    è¡¥ä¸ģ
    -0.06
    ick
    -0.06
    æ³¼
    -0.06
    POSITIVE LOGITS
    åĴ½
    0.11
    èĦĸ
    0.10
    åĴ½åĸī
    0.10
    èĦĸåŃIJ
    0.09
    åĸī
    0.09
    éĶģ骨
    0.09
    é¢Īéĥ¨
    0.09
     throat
    0.09
    æ·ĭå·´ç»ĵ
    0.09
    throat
    0.09
    Activations Density 0.070%

    No Known Activations